paper-with-me

Papers

Causal Temporal Representation Learning with Nonstationary Sparse Transition

2024-09-05 · Xiangchen Song, Zijian Li, Guangyi Chen, Yujia Zheng, Yewen Fan, Xinshuai Dong, Kun Zhang

Causal Temporal Representation Learning (Ctrl) methods aim to identify the temporal causal dynamics of complex nonstationary temporal sequences. Despite the success of existing Ctrl methods, they require either directly observing the domain variables or assuming a Markov prior on them. Such requirements limit the application of these methods in real-world scenarios when we do not have such prior knowledge of the domain variables. To address this problem, this work adopts a sparse transition assumption, aligned with intuitive human understanding, and presents identifiability results from a theoretical perspective. In particular, we explore under what conditions on the significance of the variability of the transitions we can build a model to identify the distribution shifts. Based on the theoretical result, we introduce a novel framework, Causal Temporal Representation Learning with Nonstationary Sparse Transition (CtrlNS), designed to leverage the constraints on transition sparsity and conditional independence to reliably identify both distribution shifts and latent factors. Our experimental evaluations on synthetic and real-world datasets demonstrate significant improvements over existing baselines, highlighting the effectiveness of our approach.

📄 PDF Abstract BibTeX arXiv:2409.03142

Code (1)

xiangchensong/ctrlns 공식 구현 pytorch

Tasks

Representation LearningTemporal Sequences

Methods 이 논문이 사용한 방법론

ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…
Attention 설명 없음
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
AdaGrad AdaGrad is a stochastic optimization method that adapts the learning rate to the parameters. It performs smaller updates for parameters associated with frequently occurring…
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…

Similar Papers 제목 키워드 기반

CASC: Causal Adversarial Subspace Clustering for Multivariate Spatiotemporal Data

2026-07-23 · Francis Ndikum Nji, Vandana Janeja, Jianwu Wang arxiv

Deep subspace clustering plays a critical role in applications involving multivariate spatiotemporal data, such as sea ice monitoring, disease spread analysis, and tracking neuro-degeneration over time. Despite recent ad…

Switching state space model for simultaneously estimating state transitions and nonstationary firing rates

2010-12-01 · NeurIPS 2010 12 · Ken Takiyama, Masato Okada

We propose an algorithm for simultaneously estimating state transitions among neural states, the number of neural states, and nonstationary firing rates using a switching state space model (SSSM). This model enables us …

Temporally Disentangled Representation Learning under Unknown Nonstationarity

2023-10-28 · NeurIPS 2023 11 · Xiangchen Song, Weiran Yao, Yewen Fan, Xinshuai Dong 외

In unsupervised causal representation learning for sequential data with time-delayed latent causal influences, strong identifiability results for the disentanglement of causally-related latent variables have been establi…

DisentanglementRepresentation Learning

Jacobian Granger Causal Neural Networks for Analysis of Stationary and Nonstationary Data

2022-05-19 · Suryadi, Yew-Soon Ong, Lock Yue Chew

Granger causality is a commonly used method for uncovering information flow and dependencies in a time series. Here we introduce JGC (Jacobian Granger Causality), a neural network-based approach to Granger causality usin…

Time SeriesTime Series Analysis

When and How: Learning Identifiable Latent States for Nonstationary Time Series Forecasting

2024-02-20 · Zijian Li, Ruichu Cai, Zhenhui Yang, Haiqin Huang 외

Temporal distribution shifts are ubiquitous in time series data. One of the most popular methods assumes that the temporal distribution shift occurs uniformly to disentangle the stationary and nonstationary dependencies.…

Time SeriesTime Series Forecasting